no code implementations • 14 Feb 2024 • Theodore Papamarkou, Tolga Birdal, Michael Bronstein, Gunnar Carlsson, Justin Curry, Yue Gao, Mustafa Hajij, Roland Kwitt, Pietro Liò, Paolo Di Lorenzo, Vasileios Maroulas, Nina Miolane, Farzana Nasrin, Karthikeyan Natesan Ramamurthy, Bastian Rieck, Simone Scardapane, Michael T. Schaub, Petar Veličković, Bei Wang, Yusu Wang, Guo-Wei Wei, Ghada Zamzmi
Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models.
no code implementations • 22 Nov 2023 • Colleen Farrelly, Yashbir Singh, Quincy A. Hathaway, Gunnar Carlsson, Ashok Choudhary, Rahul Paul, Gianfranco Doretto, Yassine Himeur, Shadi Atalls, Wathiq Mansoor
Institutional bias can impact patient outcomes, educational attainment, and legal system navigation.
no code implementations • 16 Aug 2021 • Gunnar Carlsson, Facundo Mémoli, Santiago Segarra
We begin by introducing three practical properties associated with the notion of robustness in hierarchical clustering: linear scale preservation, stability, and excisiveness.
no code implementations • 14 Jan 2021 • Ephy R. Love, Benjamin Filippenko, Vasileios Maroulas, Gunnar Carlsson
This work introduces the Topological CNN (TCNN), which encompasses several topologically defined convolutional methods.
1 code implementation • ICLR 2021 • Sharon Zhou, Eric Zelikman, Fred Lu, Andrew Y. Ng, Gunnar Carlsson, Stefano Ermon
Learning disentangled representations is regarded as a fundamental task for improving the generalization, robustness, and interpretability of generative models.
3 code implementations • 29 May 2019 • Rickard Brüel-Gabrielsson, Bradley J. Nelson, Anjan Dwaraknath, Primoz Skraba, Leonidas J. Guibas, Gunnar Carlsson
Topology applied to real world data using persistent homology has started to find applications within machine learning, including deep learning.
no code implementations • 2 Nov 2018 • Gunnar Carlsson, Rickard Brüel Gabrielsson
We perform topological data analysis on the internal states of convolutional deep neural networks to develop an understanding of the computations that they perform.
no code implementations • 8 Oct 2018 • Rickard Brüel Gabrielsson, Gunnar Carlsson
We use topological data analysis to show that the information encoded in the weights of a CNN can be organized in terms of a topological data model and demonstrate how such information can be interpreted and utilized.
no code implementations • 9 Feb 2018 • Leo Carlsson, Gunnar Carlsson, Mikael Vejdemo-Johansson
We describe Fibres of Failure (FiFa), a method to classify failure modes of predictive processes using the Mapper algorithm from Topological Data Analysis.
no code implementations • 21 Jul 2016 • Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro, Santiago Segarra
This paper considers networks where relationships between nodes are represented by directed dissimilarities.
no code implementations • 21 Jul 2016 • Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro, Santiago Segarra
This paper characterizes hierarchical clustering methods that abide by two previously introduced axioms -- thus, denominated admissible methods -- and proposes tractable algorithms for their implementation.
no code implementations • 21 Jul 2016 • Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro, Santiago Segarra
We introduce two practical properties of hierarchical clustering methods for (possibly asymmetric) network data: excisiveness and linear scale preservation.
no code implementations • 17 Apr 2014 • Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro, Santiago Segarra
This paper introduces hierarchical quasi-clustering methods, a generalization of hierarchical clustering for asymmetric networks where the output structure preserves the asymmetry of the input data.
2 code implementations • 2 Apr 2013 • Aaron Adcock, Erik Carlsson, Gunnar Carlsson
We study the ring of algebraic functions on the space of persistence barcodes, with applications to pattern recognition.
Rings and Algebras 13Pxx, 68T10
no code implementations • 31 Jan 2013 • Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro, Santiago Segarra
Our construction of hierarchical clustering methods is based on defining admissible methods to be those methods that abide by the axioms of value - nodes in a network with two nodes are clustered together at the maximum of the two dissimilarities between them - and transformation - when dissimilarities are reduced, the network may become more clustered but not less.
no code implementations • 24 Nov 2010 • Gunnar Carlsson, Facundo Memoli
In this paper, we construct a framework for studying what happens when we instead impose various structural conditions on the clustering schemes, under the general heading of functoriality.